Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ideal forAvoid:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atributo
    0.56
    AMENTO
    0.50
     atras
    0.48
    ১০
    0.48
     Varan
    0.46
     retiro
    0.46
     térm
    0.46
    फलता
    0.46
     obstructing
    0.46
    ьер
    0.45
    POSITIVE LOGITS
    केश
    0.45
    Mark
    0.44
    äger
    0.42
    0
    0.42
    mk
    0.41
    কেশ
    0.40
    shirts
    0.39
     म्हणजे
    0.39
    kses
    0.39
     nurseries
    0.39
    Act Density 0.006%

    No Known Activations